gemini-skill tested by Argusic Runner

Attempt 2 of 3 · Runs with mocks · Argusic Score 92.0 of 100

all runs of gemini-skillautomationbrowser-automationdrawinggeminimcpmcp-client

Session recording

Loading recording...

Download the original recording · fingerprint d509586a5ba5c212...

What the test found

Project installs, builds, and all infrastructure components function: daemon HTTP micro-service manages a headless Chrome instance via CDP, MCP stdio server exposes all Gemini/Atlas tools, atlas-provider connects to OpenAI-compatible APIs, and watermark-remover processes images through sharp - all tested end-to-end in this container.

All components verified: npm install (29 packages, no errors), daemon HTTP server starts and responds to /health with 200, launches headless Chrome on demand via /browser/acquire, returns valid wsEndpoint for puppeteer-core connection, MCP server registers all tools and responds to JSON-RPC tools/list and tools/call, atlas-provider tested against mock OpenAI-compatible server (listModels, createChatCompletion, createChatCompletionStream all pass), watermark-remover with sharp correctly processes images, full demo integration auto-starts daemon and connects to CDP-controlled browser. Gemini page interaction requires real Google login credentials (browser automation reaches gemini.google.com and finds prompt input/send button, but third-party Gemini API authentication is not mockable at this layer).

Argusic installed gemini-skill in 0.5 minutes and launched it; verification reached Verified with mock services. 1 of 1 recorded error was worked through (see the timeline below).

Runs with mocksall runs of gemini-skill

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.

Error and fix timeline

No errors were recorded for this run.

Discussion